limin(gate) commited on
Commit
0ac6b59
1 Parent(s): 449f30b

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - moe
5
+ - frankenmoe
6
+ - merge
7
+ - mergekit
8
+ - lazymergekit
9
+ - starsnatched/MemGPT-DPO
10
+ - starsnatched/MemGPT-3
11
+ - starsnatched/MemGPT
12
+ base_model:
13
+ - starsnatched/MemGPT-DPO
14
+ - starsnatched/MemGPT-3
15
+ - starsnatched/MemGPT
16
+ ---
17
+
18
+ # Memgpt-3x7b-MOE
19
+
20
+ Memgpt-3x7b-MOE is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
21
+ * [starsnatched/MemGPT-DPO](https://huggingface.co/starsnatched/MemGPT-DPO)
22
+ * [starsnatched/MemGPT-3](https://huggingface.co/starsnatched/MemGPT-3)
23
+ * [starsnatched/MemGPT](https://huggingface.co/starsnatched/MemGPT)
24
+
25
+ ## 🧩 Configuration
26
+
27
+ ```yaml
28
+ base_model: liminerity/Memgpt-slerp-7b-5
29
+ gate_mode: hidden
30
+ dtype: bfloat16
31
+ experts:
32
+ - source_model: starsnatched/MemGPT-DPO
33
+ positive_prompts:
34
+ - "versatile"
35
+ - "helpful"
36
+ - "factual"
37
+ - "integrated"
38
+ - "adaptive"
39
+ - "comprehensive"
40
+ - "balanced"
41
+ negative_prompts:
42
+ - "specialized"
43
+ - "narrow"
44
+ - "focused"
45
+ - "limited"
46
+ - "specific"
47
+
48
+ - source_model: starsnatched/MemGPT-3
49
+ positive_prompts:
50
+ - "analytical"
51
+ - "accurate"
52
+ - "logical"
53
+ - "knowledgeable"
54
+ - "precise"
55
+ - "calculate"
56
+ - "compute"
57
+ - "solve"
58
+ - "work"
59
+ - "python"
60
+ - "javascript"
61
+ - "programming"
62
+ - "algorithm"
63
+ - "tell me"
64
+ - "assistant"
65
+ negative_prompts:
66
+ - "creative"
67
+ - "abstract"
68
+ - "imaginative"
69
+ - "artistic"
70
+ - "emotional"
71
+ - "mistake"
72
+ - "inaccurate"
73
+
74
+ - source_model: starsnatched/MemGPT
75
+ positive_prompts:
76
+ - "instructive"
77
+ - "clear"
78
+ - "directive"
79
+ - "helpful"
80
+ - "informative"
81
+ negative_prompts:
82
+ - "exploratory"
83
+ - "open-ended"
84
+ - "narrative"
85
+ - "speculative"
86
+ - "artistic"
87
+ ```
88
+
89
+ ## 💻 Usage
90
+
91
+ ```python
92
+ !pip install -qU transformers bitsandbytes accelerate
93
+
94
+ from transformers import AutoTokenizer
95
+ import transformers
96
+ import torch
97
+
98
+ model = "liminerity/Memgpt-3x7b-MOE"
99
+
100
+ tokenizer = AutoTokenizer.from_pretrained(model)
101
+ pipeline = transformers.pipeline(
102
+ "text-generation",
103
+ model=model,
104
+ model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
105
+ )
106
+
107
+ messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
108
+ prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
109
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
110
+ print(outputs[0]["generated_text"])
111
+ ```
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32000
3
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "liminerity/Memgpt-slerp-7b-5",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 3,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 1000000.0,
23
+ "router_aux_loss_coef": 0.001,
24
+ "sliding_window": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.37.1",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ base_model: liminerity/Memgpt-slerp-7b-5
3
+ gate_mode: hidden
4
+ dtype: bfloat16
5
+ experts:
6
+ - source_model: starsnatched/MemGPT-DPO
7
+ positive_prompts:
8
+ - "versatile"
9
+ - "helpful"
10
+ - "factual"
11
+ - "integrated"
12
+ - "adaptive"
13
+ - "comprehensive"
14
+ - "balanced"
15
+ negative_prompts:
16
+ - "specialized"
17
+ - "narrow"
18
+ - "focused"
19
+ - "limited"
20
+ - "specific"
21
+
22
+ - source_model: starsnatched/MemGPT-3
23
+ positive_prompts:
24
+ - "analytical"
25
+ - "accurate"
26
+ - "logical"
27
+ - "knowledgeable"
28
+ - "precise"
29
+ - "calculate"
30
+ - "compute"
31
+ - "solve"
32
+ - "work"
33
+ - "python"
34
+ - "javascript"
35
+ - "programming"
36
+ - "algorithm"
37
+ - "tell me"
38
+ - "assistant"
39
+ negative_prompts:
40
+ - "creative"
41
+ - "abstract"
42
+ - "imaginative"
43
+ - "artistic"
44
+ - "emotional"
45
+ - "mistake"
46
+ - "inaccurate"
47
+
48
+ - source_model: starsnatched/MemGPT
49
+ positive_prompts:
50
+ - "instructive"
51
+ - "clear"
52
+ - "directive"
53
+ - "helpful"
54
+ - "informative"
55
+ negative_prompts:
56
+ - "exploratory"
57
+ - "open-ended"
58
+ - "narrative"
59
+ - "speculative"
60
+ - "artistic"
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad62e22e0aa7447434927fc4a564fe995c082ff313e2297b27a39763ee40e3de
3
+ size 9919813712
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a0e31e79c2d0419e5d149953a978aaa435ac5026e1132dae7aebbb0a7dfa4cb
3
+ size 9982454728
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d6e09b69b7f6c616ee52fe9959cc220bd59b55ecdb143ca886365e1812f2815
3
+ size 9982454728
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cd75c08ee26d96f6358b915f116f1c111e6e5693ffab55575ec3dce12b089bc
3
+ size 7148170232
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00004.safetensors", "model.norm.weight": "model-00001-of-00004.safetensors", "lm_head.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|im_end|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "additional_special_tokens": [],
39
+ "bos_token": "<s>",
40
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
41
+ "clean_up_tokenization_spaces": false,
42
+ "eos_token": "<|im_end|>",
43
+ "legacy": true,
44
+ "model_max_length": 1000000000000000019884624838656,
45
+ "pad_token": "<s>",
46
+ "sp_model_kwargs": {},
47
+ "spaces_between_special_tokens": false,
48
+ "tokenizer_class": "LlamaTokenizer",
49
+ "unk_token": "<unk>",
50
+ "use_default_system_prompt": false
51
+ }